利用小波变换进行海上目标识别研究

对海面舰船目标类型的识别,通常采用目视判读的方法。由于目视判读的方法不利于大面积侦察任务的快速识别,所以根据海上目标所具有的背景单一、结构复杂的特点,提出了利用小波变换所具有的多分辩率、易于消除噪声、运算方便的特点来提取舰船边缘特征,建立舰船结构特征数据库,实现舰船目标类型的自动判读。试验证明效果很好。     

基于多小波变换的红外目标探测与识别

针对光电联合变换相关器目标识别的实际应用,对待测红外目标图片进行多小波变换,并利用模极大值法提取其边缘.通过获取更多的轮廓信息,从而提高对目标的识别能力.计算机模拟了常用于红外目标处理的多小波GHM和SA4,实验结果表明:基于GHM多小波提取的边缘能获取大量的图像轮廓信息,其识别结果明显优于SA4多小波.将目标原图的光学相关探测结果与基于GHM多小波提取的边缘图像光学相关探测结果进行比较发现,经多小波预处理后的边缘图像能有效增强相关峰强度.     

Generalized wavelet transform based on the convolution operator in the linear canonical transform domain

The wavelet transform (WT) and linear canonical transform (LCT) have been shown to be powerful tool for optics and signal processing. In this paper, firstly, we introduce a novel time-frequency transformation tool coined the generalized wavelet transform (GWT), based on the idea of the LCT and WT. Then, we derive some fundamental results of this transform, including its basis properties, inner product theorem and convolution theorem, inverse formula and admissibility condition. Further, we also discuss the time-fractional-frequency resolution of the GWT. The GWT is capable of representing signals in the time-fractional-frequency plane. Last, some potential applications of the GWT are also presented to show the advantage of the theory. The GWT can circumvent the limitations of the WT and the LCT.     

基于小波包变换的复合材料超声波检测信号特征提取

本文以碳纤维复合材料常见缺陷分层、孔隙、疏松的超声波检测缺陷信号为研究对象，对超声波检测信号进行小波包变换，提取包含信号绝大部分能量的近似系数波形特征及细节系数的统计量作为样本的特征值。应用BP神经网络分类器进行分类识别验证，取得较好的识别效果。该方法能以较小的特征维数表征原始信号特点。     

基于Contourlet变换与FLD的人脸表情识别方法

提出了一种基于Contourlet变换与FLD的人脸表情特征提取方法。Contourlet变换是一种新的多尺度几何分析方法,它在具备小波变换的多分辨率特性和时频局部特性的同时,还具有很强的多方向选择性和各向异性。图像经过Contourlet变换后的低频分量可体现表情的概貌,高频方向子带可体现表情的轮廓和纹理等细节。将低频分量与部分高频方向子带结合起来作为整体特征,可压缩图像的数据量,并能够体现表情的本质特征。首先用Fisher线性判别法(FLD)进行特征提取,然后采用K-近邻法进行分类。实验证明,该方法比经典的FLD方法有着更快的特征提取速度和更高的表情识别率。     

小波分析在强流直线感应加速器信号处理中的应用

 应用小波变换具有良好的时频局部特性,通过对强流直线感应加速器(LIA)脉冲信号的去噪声、信号突变点检测以及时间间隔测量等处理,表明小波变换在LIA信号处理中有广泛的应用前景;利用小波包分析的每个节点都代表了对应频带的信号特征的特点,对“神龙一号”快脉冲波形数据进行小波包变换,以各频带信号能量为元素构造特征向量,实现了高维波形数据的特征值提取,达到了数据压缩和降维的目的,为进一步实现LIA故障智能诊断、预测维护提供了一种可行的途径。     

Modified wavelet based morphological correlation for rotation-invariant recognition

A wavelet-based rotation invariant morphological correlation (WBRIMC) is proposed as a new architecture to improve the properties of the classical rotation invariant morphological correlation (RIMC). For the WBRIMC, the JPS of the RIMC is filtered by an appropriately dilated power spectrum function of wavelet. Simulation results confirm that the WBRIMC has higher discrimination capability with sharp and intense correlation signals, and is more tolerant to the salt-and-pepper noise and white additive Gaussian noise than is the Circular harmonic filter (CHF), the phase only CHF (POCHF) and the RIMC.     

基于K-L变换的虹膜识别方法

提出了一种基于K-L变换和最近邻分类器的虹膜识别方法。该方法采用K-L变换得到一组虹膜图像基,并利用这组基图像构造一子空间,将待识别图像在这个空间上的投影系数作为待识别图像的特征向量。采用最近邻分类器进行了分类。基于CASIA虹膜数据库的试验表明,将K-L变换应用在虹膜特征提取上可以取得较高的识别率。     

基于小波不变矩的多类目标特征选择算法

特征选择是目标识别中的重要问题。对于有着3个参数（m,n,q）的小波矩来说更是如此。基于2类模式的特征选择思想,提出多类模式下绝对可分的特征选择算法,给出图像数值化处理中参数(m,n,q)的合理取值范围。实验结果表明：无论是对差别比较大、差别比较小还是混合型的多类目标,经过此特征提取出来的小波矩都有着较好的识别效果。     

基于小波变换和数据融合技术的弱小目标检测

 鉴于弱小目标检测所固有的难点及常用的单一分辨率下的检测方法还不能准确稳定地检测出目标，提出了一种弱小目标检测新方法。考虑到实际应用中的复杂背景和大量干扰噪声，运用数据融合技术，先对图像进行小波多分辨率分解，然后将不同分辨率下的子图进行最优加权平均融合来检测弱小目标。用实地拍摄的空中弱小目标红外和可见光图像分别进行实验验证，实验图像取256×256像素点阵大小，其中目标占10×10像素左右。结果表明该方法能够准确稳定地检测弱小目标，为后续的跟踪作了很好的铺垫。     

Multiple color-image fusion and watermarking based on optical interference and wavelet transform

A novel multiple color-image fusion and watermarking using optical interference and wavelet transform is proposed. In this method, each secret color image is encoded into three phase-only masks (POMs). One POM is constructed as user identity key and the other two POMs are generated as user identity key modulated by corresponding secret color image in gyrator transform domain without using any time-consuming iterative computations or post-processing of the POMs to remove inherent silhouette problem. The R, G, and B channels of different user identity keys POM are then individually multiplied to get three multiplex POMs, which are exploited as encrypted images. Similarly the R, G, and B channels of other two POMs are independently multiplied to obtain two sets of three multiplex POMs. The encrypted images are fused with gray-level cover image to produce the final encrypted image as watermarked image. The secret color images are shielded by encrypted images (which have no information about secret images) as well as cover image (which reveals no information about encrypted images). These two remarkable features of the proposed system drastically reduce the probability of the encrypted images to be searched and attacked. Each individual user has an identity key and two phase-only keys as three decryption keys besides transformation angles regarded as additional keys. Theoretical analysis and numerical simulation results validate the feasibility of the proposed method.     

基于联合变换相关的目标跟踪方法

成像跟踪制导中,相关跟踪技术占有重要的地位。基于联合变换相关的目标跟踪方法,使用图像序列的相邻两帧图像依次进行相关运算,提取相关结果中互相关峰的位置和相邻两帧图像时间间隔等信息,即可得到目标位置、方向和速度的变化情况。计算机仿真实验结果表明:该算法有效地解决了传统相关跟踪算法中存在累积误差和容易使目标漂移出其参考模板的问题,可以实现稳定跟踪。     

3-D surface profilometry based on modulation measurement by applying wavelet transform method

A new analysis of 3-D surface profilometry based on modulation measurement technique by the application of Wavelet Transform method is proposed. As a tool excelling for its multi-resolution and localization in the time and frequency domains, Wavelet Transform method with good localized time-frequency analysis ability and effective de-noizing capacity can extract the modulation distribution more accurately than Fourier Transform method. Especially for the analysis of complex object, more details of the measured object can be well remained. In this paper, the theoretical derivation of Wavelet Transform method that obtains the modulation values from a captured fringe pattern is given. Both computer simulation and elementary experiment are used to show the validity of the proposed method by making a comparison with the results of Fourier Transform method. The results show that the Wavelet Transform method has a better performance than the Fourier Transform method in modulation values retrieval.     

红外点目标检测的小波变换方法研究

在对红外图像目标特性及背景特性分析的基础上,提出了基于小波变换高频子图像处理算法及基于小波变换的区域相关算法,着重解决当目标距离成像系统较远时的点目标检测问题.实验结果表明:将区域相关算法和图像局部区域阈值的自适应滤波检测技术相结合,可显著提高红外点目标检测概率,实现较远距离的点目标检测.     

基于小波变换的体内外酒精含量近红外光谱检测与分析

应用小波分析对体外和体内的酒精近红外光谱信号进行去噪分析,通过体外光谱分析确定酒精吸收峰特征范围,为体内近红外光谱分析确定有效区间。软阈值和硬阈值下,分别采用缺省阈值、Birge-Massart阈值和最大最小值阈值,比较酒精光谱去噪,信噪比(signal noise ratio,SNR)和均方根误差(root mean square error,RMSE)去噪效果。结果表明:缺省硬阈值方法对酒精近红外光谱去噪的效果较好;小波变换可以有效去除酒精近红外光谱的噪声,提高信噪比,保留有用真实信号。在不同的酒精浓度下,去噪后的近红外光谱能够较好的显示浓度变化规律。小波分析在近红外光谱法对人体酒精无创检测及定量分析方面有较好的应用前景。     

基于Gabor小波纹理特征的目标识别新方法

给出了一种基于Gabor小波纹理特征的目标识别新方法．主要是利用Gabor小波设计了一种多通道小波滤波器。对图像目标直接进行小波变换，用Gabor小波变换系数的模的平均值和其标准方差来表示抽取的图像目标的特征，把获得的小波特征归一化后输入到改进的BP神经网络分类器进行分类识别．最后。进行了一系列的仿真实验，结果表明，这种特征提取方法能有效提取图像目标纹理特征，并且对噪音和形状的变化具有鲁棒性．在应用于目标识别时，神经网络的训练时间减少到lOmin，识别率达到94％．     

Improved multi-scale wavelet in pantograph slide edge detection

The mainstream methods of pantograph slide edge detection are based on canny operator and multi-scale wavelet. The former has good single edge response but the edge is fractured, the latter performs good edge continuity but contains excessive edge points. This paper combines the advantages of both methods and proposes as an improved multi-scale wavelet edge detection method based on canny criteria. Firstly we filtered the pantograph image with edge-preserving symmetric near neighbor filter. Secondly calculated the Gaussian wavelet modulus and arguments at all levels of scale, then suppressed the non-maxima value of modulus along the corresponding arguments. At last, we integrated the modulus drawings at all levels of scale, and connected edge with applicable dual-threshold. Experiments results show that the improved algorithm has both satisfactory performances in single edge response and edge continuity, it markedly improves the efficiency of edge detection algorithm. Peak signal to noise ratio (PSNR) analysis finds that the improved algorithm exceeds canny operator and traditional multi-scale wavelet edge detection. Moreover, it has higher positioning accuracy, clearer details and better noise performance.     

混沌干扰中基于同步挤压小波变换的谐波信号提取方法

针对混沌干扰背景下多个谐波信号的提取问题, 提出了一种基于同步挤压小波变换(SST)的谐波信号抽取方法. 首先利用SST将混沌信号和谐波信号组成的混合信号分解为不同的内蕴模态类函数, 然后利用Hilbert变换对分离出的内蕴模态类函数进行频率识别, 从中分离出各谐波信号. 以Duffing混沌背景为例, 对混沌干扰下多谐波信号的提取进行了实验分析. 实验结果表明: 对于不同频率间隔的多个谐波分量, 本文方法的提取结果都具有较高的精度, 而且所提方法对高斯白噪声的干扰具有较好的鲁棒性, 综合提取效果优于经典的经验模态分解方法.     

基于小波变换与小域特征模糊融合的人脸识别

小波变换是一种很好的图像压缩方法,利用小波变换对人脸图像进行三次小波分解,并将低频分量分割成为7个子图像。鉴于人脸上的各小域子图像信息的相互独立性。先利用小域子图像实现软分类,然后使用传统奇异值分解(SVD)法提取出各小域子图像的奇异值(SV),构造出小域奇异值特征向量,给出待识别图像对训练样本图像的隶属度,并采用模糊融合的方法对小域特征进行数据融合,获得识别结果。实验结果表明,该方法实现起来简单、识别速度快,具有很高的识别率。     

基于支持向量机的自动目标识别算法

基于对目标识别精确性的要求,提出了基于支持向量机的自动目标识别算法。介绍了基于支持向量机的自动目标识别系统的组成和识别流程,实现了目标的特征提取、SVM分类器的参数寻优,并将优化的SVM模型应用于未知图像的目标识别中。实验表明,该方法识别效果良好,具有较好的抗复杂背景的能力。